Research on Object Tracking Using a PTZ Camera

The goal of object tracking is to establish a stable track for objects of interest in successive frames. It has been an essential technology for human survival and has significant potential for human progress. For example, the technique can be used for airspace surveillance, military tracking of targets, submarine and whale tracking, autonomous robot navigation, intelligent traffic analysis, and intelligent video surveillance. They are also used in the study of cell biology to study cell fate under different chemical and environmental influences. In tracking, there are several practical problems that can render failed targeting, such as morphological variation due to the motion of objects, change in shadowing and lighting condition, and blocking of the target. The purpose of this project is to develop a dynamic optical tracking system based a PTZ camera platform to stably track any selected object and keep the targeted object image in the center of video images. The project is based on a pre-study of three well-known tracking algorithms: CAMShift, Compressive Tracking, and TLD (Tracking Learning Detection). CAMShift has the benefit of simplicity and can be executed with higher sampling rate, but is lack of learning capability to adapt for variation in target image. Compressive Tracking algorithm employs dimensionality reduction to simplify computation, but is unable to cope with the problem of change in target image size due to fixed reference image size. TLD algorithm has the learning capability but requires heavy computation. The proposed system will be based on the TLD scheme that includes three processing module: Tracking, Learning, and Detection. In the proposed scheme, the CAMShift algorithm will be implemented as the Tracking module, and the image features will be compressed by a sparse measurement matrix to accelerate execution for real-time tracking. Frame rate of the system is to be further improved by implementing the TLD algorithm in multi-thread parallel processing mode. The project will be conducted in two years aiming at enhancing accuracy and reliability of the tracking system. For the first year, we will build the basic dynamic tracking system, and investigate stability and reliability of the system. In the second year, we will research into the practical issues of morphological variation, change in shadowing and lighting condition, and obscure effects.

Project ID:PB10308-2737
External Project ID:MOST103-2221-E182-045